diff options
Diffstat (limited to 'tools')
55 files changed, 2102 insertions, 715 deletions
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index f92880a15645..2fc09579e24a 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1210,14 +1210,16 @@ union perf_mem_data_src { mem_remote:1, /* remote */ mem_snoopx:2, /* snoop mode, ext */ mem_blk:3, /* access blocked */ - mem_rsvd:21; + mem_hops:3, /* hop level */ + mem_rsvd:18; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:21, + __u64 mem_rsvd:18, + mem_hops:3, /* hop level */ mem_blk:3, /* access blocked */ mem_snoopx:2, /* snoop mode, ext */ mem_remote:1, /* remote */ @@ -1241,7 +1243,13 @@ union perf_mem_data_src { #define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ #define PERF_MEM_OP_SHIFT 0 -/* memory hierarchy (memory level, hit or miss) */ +/* + * PERF_MEM_LVL_* namespace being depricated to some extent in the + * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. + * Supporting this namespace inorder to not break defined ABIs. + * + * memory hierarchy (memory level, hit or miss) + */ #define PERF_MEM_LVL_NA 0x01 /* not available */ #define PERF_MEM_LVL_HIT 0x02 /* hit level */ #define PERF_MEM_LVL_MISS 0x04 /* miss level */ @@ -1307,6 +1315,11 @@ union perf_mem_data_src { #define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ #define PERF_MEM_BLK_SHIFT 40 +/* hop level */ +#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ +/* 2-7 available */ +#define PERF_MEM_HOPS_SHIFT 43 + #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index 1d84ec9db93b..5859ca0a1439 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -784,6 +784,7 @@ struct snd_rawmidi_status { #define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int) #define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info) +#define SNDRV_RAWMIDI_IOCTL_USER_PVERSION _IOW('W', 0x02, int) #define SNDRV_RAWMIDI_IOCTL_PARAMS _IOWR('W', 0x10, struct snd_rawmidi_params) #define SNDRV_RAWMIDI_IOCTL_STATUS _IOWR('W', 0x20, struct snd_rawmidi_status) #define SNDRV_RAWMIDI_IOCTL_DROP _IOW('W', 0x30, int) diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index b0bf56c5f120..5a5bd74f55bd 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -742,7 +742,7 @@ class DebugfsProvider(Provider): The fields are all available KVM debugfs files """ - exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns'] + exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns', 'halt_wait_ns'] fields = [field for field in self.walkdir(PATH_DEBUGFS_KVM)[2] if field not in exempt_list] diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 88d8825fc6f6..e4f83c304ec9 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -6894,7 +6894,8 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) if (obj->gen_loader) { /* reset FDs */ - btf__set_fd(obj->btf, -1); + if (obj->btf) + btf__set_fd(obj->btf, -1); for (i = 0; i < obj->nr_maps; i++) obj->maps[i].fd = -1; if (!err) diff --git a/tools/lib/bpf/strset.c b/tools/lib/bpf/strset.c index 1fb8b49de1d6..ea655318153f 100644 --- a/tools/lib/bpf/strset.c +++ b/tools/lib/bpf/strset.c @@ -88,6 +88,7 @@ void strset__free(struct strset *set) hashmap__free(set->strs_hash); free(set->strs_data); + free(set); } size_t strset__data_size(const struct strset *set) diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c index c67c83399170..ce91a582f0e4 100644 --- a/tools/lib/perf/tests/test-evlist.c +++ b/tools/lib/perf/tests/test-evlist.c @@ -40,7 +40,7 @@ static int test_stat_cpu(void) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK, }; - int err, cpu, tmp; + int err, idx; cpus = perf_cpu_map__new(NULL); __T("failed to create cpus", cpus); @@ -70,10 +70,10 @@ static int test_stat_cpu(void) perf_evlist__for_each_evsel(evlist, evsel) { cpus = perf_evsel__cpus(evsel); - perf_cpu_map__for_each_cpu(cpu, tmp, cpus) { + for (idx = 0; idx < perf_cpu_map__nr(cpus); idx++) { struct perf_counts_values counts = { .val = 0 }; - perf_evsel__read(evsel, cpu, 0, &counts); + perf_evsel__read(evsel, idx, 0, &counts); __T("failed to read value for evsel", counts.val != 0); } } diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c index a184e4861627..33ae9334861a 100644 --- a/tools/lib/perf/tests/test-evsel.c +++ b/tools/lib/perf/tests/test-evsel.c @@ -22,7 +22,7 @@ static int test_stat_cpu(void) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_CLOCK, }; - int err, cpu, tmp; + int err, idx; cpus = perf_cpu_map__new(NULL); __T("failed to create cpus", cpus); @@ -33,10 +33,10 @@ static int test_stat_cpu(void) err = perf_evsel__open(evsel, cpus, NULL); __T("failed to open evsel", err == 0); - perf_cpu_map__for_each_cpu(cpu, tmp, cpus) { + for (idx = 0; idx < perf_cpu_map__nr(cpus); idx++) { struct perf_counts_values counts = { .val = 0 }; - perf_evsel__read(evsel, cpu, 0, &counts); + perf_evsel__read(evsel, idx, 0, &counts); __T("failed to read value for evsel", counts.val != 0); } @@ -148,6 +148,7 @@ static int test_stat_user_read(int event) __T("failed to mmap evsel", err == 0); pc = perf_evsel__mmap_base(evsel, 0, 0); + __T("failed to get mmapped address", pc); #if defined(__i386__) || defined(__x86_64__) __T("userspace counter access not supported", pc->cap_user_rdpmc); diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index bc821056aba9..4d6d7fc13255 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -20,6 +20,7 @@ #include <objtool/arch.h> #include <objtool/warn.h> #include <objtool/endianness.h> +#include <objtool/builtin.h> #include <arch/elf.h> static int is_x86_64(const struct elf *elf) @@ -102,12 +103,13 @@ unsigned long arch_jump_destination(struct instruction *insn) #define rm_is_mem(reg) (mod_is_mem() && !is_RIP() && rm_is(reg)) #define rm_is_reg(reg) (mod_is_reg() && modrm_rm == (reg)) -int arch_decode_instruction(const struct elf *elf, const struct section *sec, +int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, enum insn_type *type, unsigned long *immediate, struct list_head *ops_list) { + const struct elf *elf = file->elf; struct insn insn; int x86_64, ret; unsigned char op1, op2, @@ -544,6 +546,36 @@ int arch_decode_instruction(const struct elf *elf, const struct section *sec, *type = INSN_RETURN; break; + case 0xc7: /* mov imm, r/m */ + if (!noinstr) + break; + + if (insn.length == 3+4+4 && !strncmp(sec->name, ".init.text", 10)) { + struct reloc *immr, *disp; + struct symbol *func; + int idx; + + immr = find_reloc_by_dest(elf, (void *)sec, offset+3); + disp = find_reloc_by_dest(elf, (void *)sec, offset+7); + + if (!immr || strcmp(immr->sym->name, "pv_ops")) + break; + + idx = (immr->addend + 8) / sizeof(void *); + + func = disp->sym; + if (disp->sym->type == STT_SECTION) + func = find_symbol_by_offset(disp->sym->sec, disp->addend); + if (!func) { + WARN("no func for pv_ops[]"); + return -1; + } + + objtool_pv_add(file, idx, func); + } + + break; + case 0xcf: /* iret */ /* * Handle sync_core(), which has an IRET to self. @@ -659,154 +691,52 @@ const char *arch_nop_insn(int len) return nops[len-1]; } -/* asm/alternative.h ? */ - -#define ALTINSTR_FLAG_INV (1 << 15) -#define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV) - -struct alt_instr { - s32 instr_offset; /* original instruction */ - s32 repl_offset; /* offset to replacement instruction */ - u16 cpuid; /* cpuid bit set for replacement */ - u8 instrlen; /* length of original instruction */ - u8 replacementlen; /* length of new instruction */ -} __packed; - -static int elf_add_alternative(struct elf *elf, - struct instruction *orig, struct symbol *sym, - int cpuid, u8 orig_len, u8 repl_len) -{ - const int size = sizeof(struct alt_instr); - struct alt_instr *alt; - struct section *sec; - Elf_Scn *s; - - sec = find_section_by_name(elf, ".altinstructions"); - if (!sec) { - sec = elf_create_section(elf, ".altinstructions", - SHF_ALLOC, size, 0); - - if (!sec) { - WARN_ELF("elf_create_section"); - return -1; - } - } - - s = elf_getscn(elf->elf, sec->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return -1; - } - - sec->data = elf_newdata(s); - if (!sec->data) { - WARN_ELF("elf_newdata"); - return -1; - } - - sec->data->d_size = size; - sec->data->d_align = 1; - - alt = sec->data->d_buf = malloc(size); - if (!sec->data->d_buf) { - perror("malloc"); - return -1; - } - memset(sec->data->d_buf, 0, size); - - if (elf_add_reloc_to_insn(elf, sec, sec->sh.sh_size, - R_X86_64_PC32, orig->sec, orig->offset)) { - WARN("elf_create_reloc: alt_instr::instr_offset"); - return -1; - } - - if (elf_add_reloc(elf, sec, sec->sh.sh_size + 4, - R_X86_64_PC32, sym, 0)) { - WARN("elf_create_reloc: alt_instr::repl_offset"); - return -1; - } - - alt->cpuid = bswap_if_needed(cpuid); - alt->instrlen = orig_len; - alt->replacementlen = repl_len; - - sec->sh.sh_size += size; - sec->changed = true; - - return 0; -} - -#define X86_FEATURE_RETPOLINE ( 7*32+12) +#define BYTE_RET 0xC3 -int arch_rewrite_retpolines(struct objtool_file *file) +const char *arch_ret_insn(int len) { - struct instruction *insn; - struct reloc *reloc; - struct symbol *sym; - char name[32] = ""; - - list_for_each_entry(insn, &file->retpoline_call_list, call_node) { - - if (insn->type != INSN_JUMP_DYNAMIC && - insn->type != INSN_CALL_DYNAMIC) - continue; - - if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk")) - continue; - - reloc = insn->reloc; - - sprintf(name, "__x86_indirect_alt_%s_%s", - insn->type == INSN_JUMP_DYNAMIC ? "jmp" : "call", - reloc->sym->name + 21); - - sym = find_symbol_by_name(file->elf, name); - if (!sym) { - sym = elf_create_undef_symbol(file->elf, name); - if (!sym) { - WARN("elf_create_undef_symbol"); - return -1; - } - } + static const char ret[5][5] = { + { BYTE_RET }, + { BYTE_RET, BYTES_NOP1 }, + { BYTE_RET, BYTES_NOP2 }, + { BYTE_RET, BYTES_NOP3 }, + { BYTE_RET, BYTES_NOP4 }, + }; - if (elf_add_alternative(file->elf, insn, sym, - ALT_NOT(X86_FEATURE_RETPOLINE), 5, 5)) { - WARN("elf_add_alternative"); - return -1; - } + if (len < 1 || len > 5) { + WARN("invalid RET size: %d\n", len); + return NULL; } - return 0; + return ret[len-1]; } -int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg) +int arch_decode_hint_reg(u8 sp_reg, int *base) { - struct cfi_reg *cfa = &insn->cfi.cfa; - switch (sp_reg) { case ORC_REG_UNDEFINED: - cfa->base = CFI_UNDEFINED; + *base = CFI_UNDEFINED; break; case ORC_REG_SP: - cfa->base = CFI_SP; + *base = CFI_SP; break; case ORC_REG_BP: - cfa->base = CFI_BP; + *base = CFI_BP; break; case ORC_REG_SP_INDIRECT: - cfa->base = CFI_SP_INDIRECT; + *base = CFI_SP_INDIRECT; break; case ORC_REG_R10: - cfa->base = CFI_R10; + *base = CFI_R10; break; case ORC_REG_R13: - cfa->base = CFI_R13; + *base = CFI_R13; break; case ORC_REG_DI: - cfa->base = CFI_DI; + *base = CFI_DI; break; case ORC_REG_DX: - cfa->base = CFI_DX; + *base = CFI_DX; break; default: return -1; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index e5947fbb9e7a..fb3f251ea021 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -5,6 +5,7 @@ #include <string.h> #include <stdlib.h> +#include <sys/mman.h> #include <arch/elf.h> #include <objtool/builtin.h> @@ -26,7 +27,11 @@ struct alternative { bool skip_orig; }; -struct cfi_init_state initial_func_cfi; +static unsigned long nr_cfi, nr_cfi_reused, nr_cfi_cache; + +static struct cfi_init_state initial_func_cfi; +static struct cfi_state init_cfi; +static struct cfi_state func_cfi; struct instruction *find_insn(struct objtool_file *file, struct section *sec, unsigned long offset) @@ -173,6 +178,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "rewind_stack_do_exit", "kunit_try_catch_throw", "xen_start_kernel", + "cpu_bringup_and_idle", }; if (!func) @@ -265,6 +271,78 @@ static void init_insn_state(struct insn_state *state, struct section *sec) state->noinstr = sec->noinstr; } +static struct cfi_state *cfi_alloc(void) +{ + struct cfi_state *cfi = calloc(sizeof(struct cfi_state), 1); + if (!cfi) { + WARN("calloc failed"); + exit(1); + } + nr_cfi++; + return cfi; +} + +static int cfi_bits; +static struct hlist_head *cfi_hash; + +static inline bool cficmp(struct cfi_state *cfi1, struct cfi_state *cfi2) +{ + return memcmp((void *)cfi1 + sizeof(cfi1->hash), + (void *)cfi2 + sizeof(cfi2->hash), + sizeof(struct cfi_state) - sizeof(struct hlist_node)); +} + +static inline u32 cfi_key(struct cfi_state *cfi) +{ + return jhash((void *)cfi + sizeof(cfi->hash), + sizeof(*cfi) - sizeof(cfi->hash), 0); +} + +static struct cfi_state *cfi_hash_find_or_add(struct cfi_state *cfi) +{ + struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)]; + struct cfi_state *obj; + + hlist_for_each_entry(obj, head, hash) { + if (!cficmp(cfi, obj)) { + nr_cfi_cache++; + return obj; + } + } + + obj = cfi_alloc(); + *obj = *cfi; + hlist_add_head(&obj->hash, head); + + return obj; +} + +static void cfi_hash_add(struct cfi_state *cfi) +{ + struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)]; + + hlist_add_head(&cfi->hash, head); +} + +static void *cfi_hash_alloc(unsigned long size) +{ + cfi_bits = max(10, ilog2(size)); + cfi_hash = mmap(NULL, sizeof(struct hlist_head) << cfi_bits, + PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANON, -1, 0); + if (cfi_hash == (void *)-1L) { + WARN("mmap fail cfi_hash"); + cfi_hash = NULL; + } else if (stats) { + printf("cfi_bits: %d\n", cfi_bits); + } + + return cfi_hash; +} + +static unsigned long nr_insns; +static unsigned long nr_insns_visited; + /* * Call the arch-specific instruction decoder for all the instructions and add * them to the global instruction list. @@ -275,7 +353,6 @@ static int decode_instructions(struct objtool_file *file) struct symbol *func; unsigned long offset; struct instruction *insn; - unsigned long nr_insns = 0; int ret; for_each_sec(file, sec) { @@ -292,7 +369,7 @@ static int decode_instructions(struct objtool_file *file) !strcmp(sec->name, ".entry.text")) sec->noinstr = true; - for (offset = 0; offset < sec->len; offset += insn->len) { + for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) { insn = malloc(sizeof(*insn)); if (!insn) { WARN("malloc failed"); @@ -301,13 +378,12 @@ static int decode_instructions(struct objtool_file *file) memset(insn, 0, sizeof(*insn)); INIT_LIST_HEAD(&insn->alts); INIT_LIST_HEAD(&insn->stack_ops); - init_cfi_state(&insn->cfi); insn->sec = sec; insn->offset = offset; - ret = arch_decode_instruction(file->elf, sec, offset, - sec->len - offset, + ret = arch_decode_instruction(file, sec, offset, + sec->sh.sh_size - offset, &insn->len, &insn->type, &insn->immediate, &insn->stack_ops); @@ -344,14 +420,90 @@ err: return ret; } +/* + * Read the pv_ops[] .data table to find the static initialized values. + */ +static int add_pv_ops(struct objtool_file *file, const char *symname) +{ + struct symbol *sym, *func; + unsigned long off, end; + struct reloc *rel; + int idx; + + sym = find_symbol_by_name(file->elf, symname); + if (!sym) + return 0; + + off = sym->offset; + end = off + sym->len; + for (;;) { + rel = find_reloc_by_dest_range(file->elf, sym->sec, off, end - off); + if (!rel) + break; + + func = rel->sym; + if (func->type == STT_SECTION) + func = find_symbol_by_offset(rel->sym->sec, rel->addend); + + idx = (rel->offset - sym->offset) / sizeof(unsigned long); + + objtool_pv_add(file, idx, func); + + off = rel->offset + 1; + if (off > end) + break; + } + + return 0; +} + +/* + * Allocate and initialize file->pv_ops[]. + */ +static int init_pv_ops(struct objtool_file *file) +{ + static const char *pv_ops_tables[] = { + "pv_ops", + "xen_cpu_ops", + "xen_irq_ops", + "xen_mmu_ops", + NULL, + }; + const char *pv_ops; + struct symbol *sym; + int idx, nr; + + if (!noinstr) + return 0; + + file->pv_ops = NULL; + + sym = find_symbol_by_name(file->elf, "pv_ops"); + if (!sym) + return 0; + + nr = sym->len / sizeof(unsigned long); + file->pv_ops = calloc(sizeof(struct pv_state), nr); + if (!file->pv_ops) + return -1; + + for (idx = 0; idx < nr; idx++) + INIT_LIST_HEAD(&file->pv_ops[idx].targets); + + for (idx = 0; (pv_ops = pv_ops_tables[idx]); idx++) + add_pv_ops(file, pv_ops); + + return 0; +} + static struct instruction *find_last_insn(struct objtool_file *file, struct section *sec) { struct instruction *insn = NULL; unsigned int offset; - unsigned int end = (sec->len > 10) ? sec->len - 10 : 0; + unsigned int end = (sec->sh.sh_size > 10) ? sec->sh.sh_size - 10 : 0; - for (offset = sec->len - 1; offset >= end && !insn; offset--) + for (offset = sec->sh.sh_size - 1; offset >= end && !insn; offset--) insn = find_insn(file, sec, offset); return insn; @@ -389,7 +541,7 @@ static int add_dead_ends(struct objtool_file *file) insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (reloc->addend == reloc->sym->sec->len) { + else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find unreachable insn at %s+0x%x", @@ -424,7 +576,7 @@ reachable: insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (reloc->addend == reloc->sym->sec->len) { + else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find reachable insn at %s+0x%x", @@ -531,6 +683,52 @@ static int create_static_call_sections(struct objtool_file *file) return 0; } +static int create_retpoline_sites_sections(struct objtool_file *file) +{ + struct instruction *insn; + struct section *sec; + int idx; + + sec = find_section_by_name(file->elf, ".retpoline_sites"); + if (sec) { + WARN("file already has .retpoline_sites, skipping"); + return 0; + } + + idx = 0; + list_for_each_entry(insn, &file->retpoline_call_list, call_node) + idx++; + + if (!idx) + return 0; + + sec = elf_create_section(file->elf, ".retpoline_sites", 0, + sizeof(int), idx); + if (!sec) { + WARN("elf_create_section: .retpoline_sites"); + return -1; + } + + idx = 0; + list_for_each_entry(insn, &file->retpoline_call_list, call_node) { + + int *site = (int *)sec->data->d_buf + idx; + *site = 0; + + if (elf_add_reloc_to_insn(file->elf, sec, + idx * sizeof(int), + R_X86_64_PC32, + insn->sec, insn->offset)) { + WARN("elf_add_reloc_to_insn: .retpoline_sites"); + return -1; + } + + idx++; + } + + return 0; +} + static int create_mcount_loc_sections(struct objtool_file *file) { struct section *sec; @@ -549,7 +747,7 @@ static int create_mcount_loc_sections(struct objtool_file *file) return 0; idx = 0; - list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) + list_for_each_entry(insn, &file->mcount_loc_list, call_node) idx++; sec = elf_create_section(file->elf, "__mcount_loc", 0, sizeof(unsigned long), idx); @@ -557,7 +755,7 @@ static int create_mcount_loc_sections(struct objtool_file *file) return -1; idx = 0; - list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) { + list_for_each_entry(insn, &file->mcount_loc_list, call_node) { loc = (unsigned long *)sec->data->d_buf + idx; memset(loc, 0, sizeof(unsigned long)); @@ -817,6 +1015,9 @@ static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *i return NULL; if (!insn->reloc) { + if (!file) + return NULL; + insn->reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); if (!insn->reloc) { @@ -828,6 +1029,136 @@ static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *i return insn->reloc; } +static void remove_insn_ops(struct instruction *insn) +{ + struct stack_op *op, *tmp; + + list_for_each_entry_safe(op, tmp, &insn->stack_ops, list) { + list_del(&op->list); + free(op); + } +} + +static void annotate_call_site(struct objtool_file *file, + struct instruction *insn, bool sibling) +{ + struct reloc *reloc = insn_reloc(file, insn); + struct symbol *sym = insn->call_dest; + + if (!sym) + sym = reloc->sym; + + /* + * Alternative replacement code is just template code which is + * sometimes copied to the original instruction. For now, don't + * annotate it. (In the future we might consider annotating the + * original instruction if/when it ever makes sense to do so.) + */ + if (!strcmp(insn->sec->name, ".altinstr_replacement")) + return; + + if (sym->static_call_tramp) { + list_add_tail(&insn->call_node, &file->static_call_list); + return; + } + + if (sym->retpoline_thunk) { + list_add_tail(&insn->call_node, &file->retpoline_call_list); + return; + } + + /* + * Many compilers cannot disable KCOV with a function attribute + * so they need a little help, NOP out any KCOV calls from noinstr + * text. + */ + if (insn->sec->noinstr && sym->kcov) { + if (reloc) { + reloc->type = R_NONE; + elf_write_reloc(file->elf, reloc); + } + + elf_write_insn(file->elf, insn->sec, + insn->offset, insn->len, + sibling ? arch_ret_insn(insn->len) + : arch_nop_insn(insn->len)); + + insn->type = sibling ? INSN_RETURN : INSN_NOP; + return; + } + + if (mcount && sym->fentry) { + if (sibling) + WARN_FUNC("Tail call to __fentry__ !?!?", insn->sec, insn->offset); + + if (reloc) { + reloc->type = R_NONE; + elf_write_reloc(file->elf, reloc); + } + + elf_write_insn(file->elf, insn->sec, + insn->offset, insn->len, + arch_nop_insn(insn->len)); + + insn->type = INSN_NOP; + + list_add_tail(&insn->call_node, &file->mcount_loc_list); + return; + } +} + +static void add_call_dest(struct objtool_file *file, struct instruction *insn, + struct symbol *dest, bool sibling) +{ + insn->call_dest = dest; + if (!dest) + return; + + /* + * Whatever stack impact regular CALLs have, should be undone + * by the RETURN of the called function. + * + * Annotated intra-function calls retain the stack_ops but + * are converted to JUMP, see read_intra_function_calls(). + */ + remove_insn_ops(insn); + + annotate_call_site(file, insn, sibling); +} + +static void add_retpoline_call(struct objtool_file *file, struct instruction *insn) +{ + /* + * Retpoline calls/jumps are really dynamic calls/jumps in disguise, + * so convert them accordingly. + */ + switch (insn->type) { + case INSN_CALL: + insn->type = INSN_CALL_DYNAMIC; + break; + case INSN_JUMP_UNCONDITIONAL: + insn->type = INSN_JUMP_DYNAMIC; + break; + case INSN_JUMP_CONDITIONAL: + insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL; + break; + default: + return; + } + + insn->retpoline_safe = true; + + /* + * Whatever stack impact regular CALLs have, should be undone + * by the RETURN of the called function. + * + * Annotated intra-function calls retain the stack_ops but + * are converted to JUMP, see read_intra_function_calls(). + */ + remove_insn_ops(insn); + + annotate_call_site(file, insn, false); +} /* * Find the destination instructions for all jumps. */ @@ -849,28 +1180,12 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->type == STT_SECTION) { dest_sec = reloc->sym->sec; dest_off = arch_dest_reloc_offset(reloc->addend); - } else if (arch_is_retpoline(reloc->sym)) { - /* - * Retpoline jumps are really dynamic jumps in - * disguise, so convert them accordingly. - */ - if (insn->type == INSN_JUMP_UNCONDITIONAL) - insn->type = INSN_JUMP_DYNAMIC; - else - insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL; - - list_add_tail(&insn->call_node, - &file->retpoline_call_list); - - insn->retpoline_safe = true; + } else if (reloc->sym->retpoline_thunk) { + add_retpoline_call(file, insn); continue; } else if (insn->func) { /* internal or external sibling call (with reloc) */ - insn->call_dest = reloc->sym; - if (insn->call_dest->static_call_tramp) { - list_add_tail(&insn->call_node, - &file->static_call_list); - } + add_call_dest(file, insn, reloc->sym, true); continue; } else if (reloc->sym->sec->idx) { dest_sec = reloc->sym->sec; @@ -926,13 +1241,8 @@ static int add_jump_destinations(struct objtool_file *file) } else if (insn->jump_dest->func->pfunc != insn->func->pfunc && insn->jump_dest->offset == insn->jump_dest->func->offset) { - /* internal sibling call (without reloc) */ - insn->call_dest = insn->jump_dest->func; - if (insn->call_dest->static_call_tramp) { - list_add_tail(&insn->call_node, - &file->static_call_list); - } + add_call_dest(file, insn, insn->jump_dest->func, true); } } } @@ -940,16 +1250,6 @@ static int add_jump_destinations(struct objtool_file *file) return 0; } -static void remove_insn_ops(struct instruction *insn) -{ - struct stack_op *op, *tmp; - - list_for_each_entry_safe(op, tmp, &insn->stack_ops, list) { - list_del(&op->list); - free(op); - } -} - static struct symbol *find_call_destination(struct section *sec, unsigned long offset) { struct symbol *call_dest; @@ -968,6 +1268,7 @@ static int add_call_destinations(struct objtool_file *file) { struct instruction *insn; unsigned long dest_off; + struct symbol *dest; struct reloc *reloc; for_each_insn(file, insn) { @@ -977,7 +1278,9 @@ static int add_call_destinations(struct objtool_file *file) reloc = insn_reloc(file, insn); if (!reloc) { dest_off = arch_jump_destination(insn); - insn->call_dest = find_call_destination(insn->sec, dest_off); + dest = find_call_destination(insn->sec, dest_off); + + add_call_dest(file, insn, dest, false); if (insn->ignore) continue; @@ -995,9 +1298,8 @@ static int add_call_destinations(struct objtool_file *file) } else if (reloc->sym->type == STT_SECTION) { dest_off = arch_dest_reloc_offset(reloc->addend); - insn->call_dest = find_call_destination(reloc->sym->sec, - dest_off); - if (!insn->call_dest) { + dest = find_call_destination(reloc->sym->sec, dest_off); + if (!dest) { WARN_FUNC("can't find call dest symbol at %s+0x%lx", insn->sec, insn->offset, reloc->sym->sec->name, @@ -1005,70 +1307,13 @@ static int add_call_destinations(struct objtool_file *file) return -1; } - } else if (arch_is_retpoline(reloc->sym)) { - /* - * Retpoline calls are really dynamic calls in - * disguise, so convert them accordingly. - */ - insn->type = INSN_CALL_DYNAMIC; - insn->retpoline_safe = true; + add_call_dest(file, insn, dest, false); - list_add_tail(&insn->call_node, - &file->retpoline_call_list); - - remove_insn_ops(insn); - continue; + } else if (reloc->sym->retpoline_thunk) { + add_retpoline_call(file, insn); } else - insn->call_dest = reloc->sym; - - if (insn->call_dest && insn->call_dest->static_call_tramp) { - list_add_tail(&insn->call_node, - &file->static_call_list); - } - - /* - * Many compilers cannot disable KCOV with a function attribute - * so they need a little help, NOP out any KCOV calls from noinstr - * text. - */ - if (insn->sec->noinstr && - !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) { - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } - - elf_write_insn(file->elf, insn->sec, - insn->offset, insn->len, - arch_nop_insn(insn->len)); - insn->type = INSN_NOP; - } - - if (mcount && !strcmp(insn->call_dest->name, "__fentry__")) { - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } - - elf_write_insn(file->elf, insn->sec, - insn->offset, insn->len, - arch_nop_insn(insn->len)); - - insn->type = INSN_NOP; - - list_add_tail(&insn->mcount_loc_node, - &file->mcount_loc_list); - } - - /* - * Whatever stack impact regular CALLs have, should be undone - * by the RETURN of the called function. - * - * Annotated intra-function calls retain the stack_ops but - * are converted to JUMP, see read_intra_function_calls(). - */ - remove_insn_ops(insn); + add_call_dest(file, insn, reloc->sym, false); } return 0; @@ -1136,7 +1381,6 @@ static int handle_group_alt(struct objtool_file *file, memset(nop, 0, sizeof(*nop)); INIT_LIST_HEAD(&nop->alts); INIT_LIST_HEAD(&nop->stack_ops); - init_cfi_state(&nop->cfi); nop->sec = special_alt->new_sec; nop->offset = special_alt->new_off + special_alt->new_len; @@ -1545,10 +1789,11 @@ static void set_func_state(struct cfi_state *state) static int read_unwind_hints(struct objtool_file *file) { + struct cfi_state cfi = init_cfi; struct section *sec, *relocsec; - struct reloc *reloc; struct unwind_hint *hint; struct instruction *insn; + struct reloc *reloc; int i; sec = find_section_by_name(file->elf, ".discard.unwind_hints"); @@ -1561,14 +1806,14 @@ static int read_unwind_hints(struct objtool_file *file) return -1; } - if (sec->len % sizeof(struct unwind_hint)) { + if (sec->sh.sh_size % sizeof(struct unwind_hint)) { WARN("struct unwind_hint size mismatch"); return -1; } file->hints = true; - for (i = 0; i < sec->len / sizeof(struct unwind_hint); i++) { + for (i = 0; i < sec->sh.sh_size / sizeof(struct unwind_hint); i++) { hint = (struct unwind_hint *)sec->data->d_buf + i; reloc = find_reloc_by_dest(file->elf, sec, i * sizeof(*hint)); @@ -1586,19 +1831,24 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true; if (hint->type == UNWIND_HINT_TYPE_FUNC) { - set_func_state(&insn->cfi); + insn->cfi = &func_cfi; continue; } - if (arch_decode_hint_reg(insn, hint->sp_reg)) { + if (insn->cfi) + cfi = *(insn->cfi); + + if (arch_decode_hint_reg(hint->sp_reg, &cfi.cfa.base)) { WARN_FUNC("unsupported unwind_hint sp base reg %d", insn->sec, insn->offset, hint->sp_reg); return -1; } - insn->cfi.cfa.offset = bswap_if_needed(hint->sp_offset); - insn->cfi.type = hint->type; - insn->cfi.end = hint->end; + cfi.cfa.offset = bswap_if_needed(hint->sp_offset); + cfi.type = hint->type; + cfi.end = hint->end; + + insn->cfi = cfi_hash_find_or_add(&cfi); } return 0; @@ -1737,17 +1987,28 @@ static int read_intra_function_calls(struct objtool_file *file) return 0; } -static int read_static_call_tramps(struct objtool_file *file) +static int classify_symbols(struct objtool_file *file) { struct section *sec; struct symbol *func; for_each_sec(file, sec) { list_for_each_entry(func, &sec->symbol_list, list) { - if (func->bind == STB_GLOBAL && - !strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, + if (func->bind != STB_GLOBAL) + continue; + + if (!strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, strlen(STATIC_CALL_TRAMP_PREFIX_STR))) func->static_call_tramp = true; + + if (arch_is_retpoline(func)) + func->retpoline_thunk = true; + + if (!strcmp(func->name, "__fentry__")) + func->fentry = true; + + if (!strncmp(func->name, "__sanitizer_cov_", 16)) + func->kcov = true; } } @@ -1780,17 +2041,16 @@ static void mark_rodata(struct objtool_file *file) file->rodata = found; } -__weak int arch_rewrite_retpolines(struct objtool_file *file) -{ - return 0; -} - static int decode_sections(struct objtool_file *file) { int ret; mark_rodata(file); + ret = init_pv_ops(file); + if (ret) + return ret; + ret = decode_instructions(file); if (ret) return ret; @@ -1809,7 +2069,7 @@ static int decode_sections(struct objtool_file *file) /* * Must be before add_{jump_call}_destination. */ - ret = read_static_call_tramps(file); + ret = classify_symbols(file); if (ret) return ret; @@ -1853,23 +2113,14 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; - /* - * Must be after add_special_section_alts(), since this will emit - * alternatives. Must be after add_{jump,call}_destination(), since - * those create the call insn lists. - */ - ret = arch_rewrite_retpolines(file); - if (ret) - return ret; - return 0; } static bool is_fentry_call(struct instruction *insn) { - if (insn->type == INSN_CALL && insn->call_dest && - insn->call_dest->type == STT_NOTYPE && - !strcmp(insn->call_dest->name, "__fentry__")) + if (insn->type == INSN_CALL && + insn->call_dest && + insn->call_dest->fentry) return true; return false; @@ -2452,13 +2703,18 @@ static int propagate_alt_cfi(struct objtool_file *file, struct instruction *insn if (!insn->alt_group) return 0; + if (!insn->cfi) { + WARN("CFI missing"); + return -1; + } + alt_cfi = insn->alt_group->cfi; group_off = insn->offset - insn->alt_group->first_insn->offset; if (!alt_cfi[group_off]) { - alt_cfi[group_off] = &insn->cfi; + alt_cfi[group_off] = insn->cfi; } else { - if (memcmp(alt_cfi[group_off], &insn->cfi, sizeof(struct cfi_state))) { + if (cficmp(alt_cfi[group_off], insn->cfi)) { WARN_FUNC("stack layout conflict in alternatives", insn->sec, insn->offset); return -1; @@ -2509,9 +2765,14 @@ static int handle_insn_ops(struct instruction *insn, static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2) { - struct cfi_state *cfi1 = &insn->cfi; + struct cfi_state *cfi1 = insn->cfi; int i; + if (!cfi1) { + WARN("CFI missing"); + return false; + } + if (memcmp(&cfi1->cfa, &cfi2->cfa, sizeof(cfi1->cfa))) { WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d", @@ -2562,20 +2823,64 @@ static inline bool func_uaccess_safe(struct symbol *func) static inline const char *call_dest_name(struct instruction *insn) { + static char pvname[16]; + struct reloc *rel; + int idx; + if (insn->call_dest) return insn->call_dest->name; + rel = insn_reloc(NULL, insn); + if (rel && !strcmp(rel->sym->name, "pv_ops")) { + idx = (rel->addend / sizeof(void *)); + snprintf(pvname, sizeof(pvname), "pv_ops[%d]", idx); + return pvname; + } + return "{dynamic}"; } -static inline bool noinstr_call_dest(struct symbol *func) +static bool pv_call_dest(struct objtool_file *file, struct instruction *insn) +{ + struct symbol *target; + struct reloc *rel; + int idx; + + rel = insn_reloc(file, insn); + if (!rel || strcmp(rel->sym->name, "pv_ops")) + return false; + + idx = (arch_dest_reloc_offset(rel->addend) / sizeof(void *)); + + if (file->pv_ops[idx].clean) + return true; + + file->pv_ops[idx].clean = true; + + list_for_each_entry(target, &file->pv_ops[idx].targets, pv_target) { + if (!target->sec->noinstr) { + WARN("pv_ops[%d]: %s", idx, target->name); + file->pv_ops[idx].clean = false; + } + } + + return file->pv_ops[idx].clean; +} + +static inline bool noinstr_call_dest(struct objtool_file *file, + struct instruction *insn, + struct symbol *func) { /* * We can't deal with indirect function calls at present; * assume they're instrumented. */ - if (!func) + if (!func) { + if (file->pv_ops) + return pv_call_dest(file, insn); + return false; + } /* * If the symbol is from a noinstr section; we good. @@ -2594,10 +2899,12 @@ static inline bool noinstr_call_dest(struct symbol *func) return false; } -static int validate_call(struct instruction *insn, struct insn_state *state) +static int validate_call(struct objtool_file *file, + struct instruction *insn, + struct insn_state *state) { if (state->noinstr && state->instr <= 0 && - !noinstr_call_dest(insn->call_dest)) { + !noinstr_call_dest(file, insn, insn->call_dest)) { WARN_FUNC("call to %s() leaves .noinstr.text section", insn->sec, insn->offset, call_dest_name(insn)); return 1; @@ -2618,7 +2925,9 @@ static int validate_call(struct instruction *insn, struct insn_state *state) return 0; } -static int validate_sibling_call(struct instruction *insn, struct insn_state *state) +static int validate_sibling_call(struct objtool_file *file, + struct instruction *insn, + struct insn_state *state) { if (has_modified_stack_frame(insn, state)) { WARN_FUNC("sibling call from callable instruction with modified stack frame", @@ -2626,7 +2935,7 @@ static int validate_sibling_call(struct instruction *insn, struct insn_state *st return 1; } - return validate_call(insn, state); + return validate_call(file, insn, state); } static int validate_return(struct symbol *func, struct instruction *insn, struct insn_state *state) @@ -2696,7 +3005,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, struct instruction *insn, struct insn_state state) { struct alternative *alt; - struct instruction *next_insn; + struct instruction *next_insn, *prev_insn = NULL; struct section *sec; u8 visited; int ret; @@ -2725,15 +3034,25 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, if (insn->visited & visited) return 0; + } else { + nr_insns_visited++; } if (state.noinstr) state.instr += insn->instr; - if (insn->hint) - state.cfi = insn->cfi; - else - insn->cfi = state.cfi; + if (insn->hint) { + state.cfi = *insn->cfi; + } else { + /* XXX track if we actually changed state.cfi */ + + if (prev_insn && !cficmp(prev_insn->cfi, &state.cfi)) { + insn->cfi = prev_insn->cfi; + nr_cfi_reused++; + } else { + insn->cfi = cfi_hash_find_or_add(&state.cfi); + } + } insn->visited |= visited; @@ -2769,7 +3088,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_CALL: case INSN_CALL_DYNAMIC: - ret = validate_call(insn, &state); + ret = validate_call(file, insn, &state); if (ret) return ret; @@ -2788,7 +3107,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_JUMP_CONDITIONAL: case INSN_JUMP_UNCONDITIONAL: if (is_sibling_call(insn)) { - ret = validate_sibling_call(insn, &state); + ret = validate_sibling_call(file, insn, &state); if (ret) return ret; @@ -2810,7 +3129,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_JUMP_DYNAMIC: case INSN_JUMP_DYNAMIC_CONDITIONAL: if (is_sibling_call(insn)) { - ret = validate_sibling_call(insn, &state); + ret = validate_sibling_call(file, insn, &state); if (ret) return ret; } @@ -2883,6 +3202,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 1; } + prev_insn = insn; insn = next_insn; } @@ -3138,10 +3458,20 @@ int check(struct objtool_file *file) int ret, warnings = 0; arch_initial_func_cfi_state(&initial_func_cfi); + init_cfi_state(&init_cfi); + init_cfi_state(&func_cfi); + set_func_state(&func_cfi); + + if (!cfi_hash_alloc(1UL << (file->elf->symbol_bits - 3))) + goto out; + + cfi_hash_add(&init_cfi); + cfi_hash_add(&func_cfi); ret = decode_sections(file); if (ret < 0) goto out; + warnings += ret; if (list_empty(&file->insn_list)) @@ -3185,6 +3515,13 @@ int check(struct objtool_file *file) goto out; warnings += ret; + if (retpoline) { + ret = create_retpoline_sites_sections(file); + if (ret < 0) + goto out; + warnings += ret; + } + if (mcount) { ret = create_mcount_loc_sections(file); if (ret < 0) @@ -3192,6 +3529,13 @@ int check(struct objtool_file *file) warnings += ret; } + if (stats) { + printf("nr_insns_visited: %ld\n", nr_insns_visited); + printf("nr_cfi: %ld\n", nr_cfi); + printf("nr_cfi_reused: %ld\n", nr_cfi_reused); + printf("nr_cfi_cache: %ld\n", nr_cfi_cache); + } + out: /* * For now, don't fail the kernel build on fatal warnings. These diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 8676c7598728..81a4c543ff7e 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -286,10 +286,9 @@ static int read_sections(struct elf *elf) return -1; } } - sec->len = sec->sh.sh_size; if (sec->sh.sh_flags & SHF_EXECINSTR) - elf->text_size += sec->len; + elf->text_size += sec->sh.sh_size; list_add_tail(&sec->list, &elf->sections); elf_hash_add(section, &sec->hash, sec->idx); @@ -509,6 +508,7 @@ int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, list_add_tail(&reloc->list, &sec->reloc->reloc_list); elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc)); + sec->reloc->sh.sh_size += sec->reloc->sh.sh_entsize; sec->reloc->changed = true; return 0; @@ -734,97 +734,13 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) data->d_size = strlen(str) + 1; data->d_align = 1; - len = strtab->len; - strtab->len += data->d_size; + len = strtab->sh.sh_size; + strtab->sh.sh_size += data->d_size; strtab->changed = true; return len; } -struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) -{ - struct section *symtab, *symtab_shndx; - struct symbol *sym; - Elf_Data *data; - Elf_Scn *s; - - sym = malloc(sizeof(*sym)); - if (!sym) { - perror("malloc"); - return NULL; - } - memset(sym, 0, sizeof(*sym)); - - sym->name = strdup(name); - - sym->sym.st_name = elf_add_string(elf, NULL, sym->name); - if (sym->sym.st_name == -1) - return NULL; - - sym->sym.st_info = GELF_ST_INFO(STB_GLOBAL, STT_NOTYPE); - // st_other 0 - // st_shndx 0 - // st_value 0 - // st_size 0 - - symtab = find_section_by_name(elf, ".symtab"); - if (!symtab) { - WARN("can't find .symtab"); - return NULL; - } - - s = elf_getscn(elf->elf, symtab->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return NULL; - } - - data = elf_newdata(s); - if (!data) { - WARN_ELF("elf_newdata"); - return NULL; - } - - data->d_buf = &sym->sym; - data->d_size = sizeof(sym->sym); - data->d_align = 1; - data->d_type = ELF_T_SYM; - - sym->idx = symtab->len / sizeof(sym->sym); - - symtab->len += data->d_size; - symtab->changed = true; - - symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); - if (symtab_shndx) { - s = elf_getscn(elf->elf, symtab_shndx->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return NULL; - } - - data = elf_newdata(s); - if (!data) { - WARN_ELF("elf_newdata"); - return NULL; - } - - data->d_buf = &sym->sym.st_size; /* conveniently 0 */ - data->d_size = sizeof(Elf32_Word); - data->d_align = 4; - data->d_type = ELF_T_WORD; - - symtab_shndx->len += 4; - symtab_shndx->changed = true; - } - - sym->sec = find_section_by_index(elf, 0); - - elf_add_symbol(elf, sym); - - return sym; -} - struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr) { @@ -855,7 +771,6 @@ struct section *elf_create_section(struct elf *elf, const char *name, } sec->idx = elf_ndxscn(s); - sec->len = size; sec->changed = true; sec->data = elf_newdata(s); @@ -979,63 +894,63 @@ static struct section *elf_create_reloc_section(struct elf *elf, } } -static int elf_rebuild_rel_reloc_section(struct section *sec, int nr) +static int elf_rebuild_rel_reloc_section(struct section *sec) { struct reloc *reloc; - int idx = 0, size; + int idx = 0; void *buf; /* Allocate a buffer for relocations */ - size = nr * sizeof(GElf_Rel); - buf = malloc(size); + buf = malloc(sec->sh.sh_size); if (!buf) { perror("malloc"); return -1; } sec->data->d_buf = buf; - sec->data->d_size = size; + sec->data->d_size = sec->sh.sh_size; sec->data->d_type = ELF_T_REL; - sec->sh.sh_size = size; - idx = 0; list_for_each_entry(reloc, &sec->reloc_list, list) { reloc->rel.r_offset = reloc->offset; reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - gelf_update_rel(sec->data, idx, &reloc->rel); + if (!gelf_update_rel(sec->data, idx, &reloc->rel)) { + WARN_ELF("gelf_update_rel"); + return -1; + } idx++; } return 0; } -static int elf_rebuild_rela_reloc_section(struct section *sec, int nr) +static int elf_rebuild_rela_reloc_section(struct section *sec) { struct reloc *reloc; - int idx = 0, size; + int idx = 0; void *buf; /* Allocate a buffer for relocations with addends */ - size = nr * sizeof(GElf_Rela); - buf = malloc(size); + buf = malloc(sec->sh.sh_size); if (!buf) { perror("malloc"); return -1; } sec->data->d_buf = buf; - sec->data->d_size = size; + sec->data->d_size = sec->sh.sh_size; sec->data->d_type = ELF_T_RELA; - sec->sh.sh_size = size; - idx = 0; list_for_each_entry(reloc, &sec->reloc_list, list) { reloc->rela.r_offset = reloc->offset; reloc->rela.r_addend = reloc->addend; reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - gelf_update_rela(sec->data, idx, &reloc->rela); + if (!gelf_update_rela(sec->data, idx, &reloc->rela)) { + WARN_ELF("gelf_update_rela"); + return -1; + } idx++; } @@ -1044,16 +959,9 @@ static int elf_rebuild_rela_reloc_section(struct section *sec, int nr) static int elf_rebuild_reloc_section(struct elf *elf, struct section *sec) { - struct reloc *reloc; - int nr; - - nr = 0; - list_for_each_entry(reloc, &sec->reloc_list, list) - nr++; - switch (sec->sh.sh_type) { - case SHT_REL: return elf_rebuild_rel_reloc_section(sec, nr); - case SHT_RELA: return elf_rebuild_rela_reloc_section(sec, nr); + case SHT_REL: return elf_rebuild_rel_reloc_section(sec); + case SHT_RELA: return elf_rebuild_rela_reloc_section(sec); default: return -1; } } @@ -1113,12 +1021,6 @@ int elf_write(struct elf *elf) /* Update changed relocation sections and section headers: */ list_for_each_entry(sec, &elf->sections, list) { if (sec->changed) { - if (sec->base && - elf_rebuild_reloc_section(elf, sec)) { - WARN("elf_rebuild_reloc_section"); - return -1; - } - s = elf_getscn(elf->elf, sec->idx); if (!s) { WARN_ELF("elf_getscn"); @@ -1129,6 +1031,12 @@ int elf_write(struct elf *elf) return -1; } + if (sec->base && + elf_rebuild_reloc_section(elf, sec)) { + WARN("elf_rebuild_reloc_section"); + return -1; + } + sec->changed = false; elf->changed = true; } diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h index 062bb6e9b865..589ff58426ab 100644 --- a/tools/objtool/include/objtool/arch.h +++ b/tools/objtool/include/objtool/arch.h @@ -69,7 +69,7 @@ struct instruction; void arch_initial_func_cfi_state(struct cfi_init_state *state); -int arch_decode_instruction(const struct elf *elf, const struct section *sec, +int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, enum insn_type *type, unsigned long *immediate, @@ -82,8 +82,9 @@ unsigned long arch_jump_destination(struct instruction *insn); unsigned long arch_dest_reloc_offset(int addend); const char *arch_nop_insn(int len); +const char *arch_ret_insn(int len); -int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg); +int arch_decode_hint_reg(u8 sp_reg, int *base); bool arch_is_retpoline(struct symbol *sym); diff --git a/tools/objtool/include/objtool/cfi.h b/tools/objtool/include/objtool/cfi.h index fd5cb0bed9bf..f11d1ac1dadf 100644 --- a/tools/objtool/include/objtool/cfi.h +++ b/tools/objtool/include/objtool/cfi.h @@ -7,6 +7,7 @@ #define _OBJTOOL_CFI_H #include <arch/cfi_regs.h> +#include <linux/list.h> #define CFI_UNDEFINED -1 #define CFI_CFA -2 @@ -24,6 +25,7 @@ struct cfi_init_state { }; struct cfi_state { + struct hlist_node hash; /* must be first, cficmp() */ struct cfi_reg regs[CFI_NUM_REGS]; struct cfi_reg vals[CFI_NUM_REGS]; struct cfi_reg cfa; diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index 56d50bc50c10..6cfff078897f 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -40,7 +40,6 @@ struct instruction { struct list_head list; struct hlist_node hash; struct list_head call_node; - struct list_head mcount_loc_node; struct section *sec; unsigned long offset; unsigned int len; @@ -60,7 +59,7 @@ struct instruction { struct list_head alts; struct symbol *func; struct list_head stack_ops; - struct cfi_state cfi; + struct cfi_state *cfi; }; static inline bool is_static_jump(struct instruction *insn) diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index e34395047530..cdc739fa9a6f 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -38,7 +38,6 @@ struct section { Elf_Data *data; char *name; int idx; - unsigned int len; bool changed, text, rodata, noinstr; }; @@ -55,8 +54,12 @@ struct symbol { unsigned long offset; unsigned int len; struct symbol *pfunc, *cfunc, *alias; - bool uaccess_safe; - bool static_call_tramp; + u8 uaccess_safe : 1; + u8 static_call_tramp : 1; + u8 retpoline_thunk : 1; + u8 fentry : 1; + u8 kcov : 1; + struct list_head pv_target; }; struct reloc { @@ -141,7 +144,6 @@ int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn); int elf_write_reloc(struct elf *elf, struct reloc *reloc); -struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name); int elf_write(struct elf *elf); void elf_close(struct elf *elf); diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h index 24fa83634de4..f99fbc6078d5 100644 --- a/tools/objtool/include/objtool/objtool.h +++ b/tools/objtool/include/objtool/objtool.h @@ -14,6 +14,11 @@ #define __weak __attribute__((weak)) +struct pv_state { + bool clean; + struct list_head targets; +}; + struct objtool_file { struct elf *elf; struct list_head insn_list; @@ -25,10 +30,14 @@ struct objtool_file { unsigned long jl_short, jl_long; unsigned long jl_nop_short, jl_nop_long; + + struct pv_state *pv_ops; }; struct objtool_file *objtool_open_read(const char *_objname); +void objtool_pv_add(struct objtool_file *file, int idx, struct symbol *func); + int check(struct objtool_file *file); int orc_dump(const char *objname); int orc_create(struct objtool_file *file); diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index e21db8bce493..c90c7084e45a 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -135,6 +135,28 @@ struct objtool_file *objtool_open_read(const char *_objname) return &file; } +void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func) +{ + if (!noinstr) + return; + + if (!f->pv_ops) { + WARN("paravirt confusion"); + return; + } + + /* + * These functions will be patched into native code, + * see paravirt_patch(). + */ + if (!strcmp(func->name, "_paravirt_nop") || + !strcmp(func->name, "_paravirt_ident_64")) + return; + + list_add(&func->pv_target, &f->pv_ops[idx].targets); + f->pv_ops[idx].clean = false; +} + static void cmd_usage(void) { unsigned int i, longest = 0; diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index dc9b7dd314b0..dd3c64af9db2 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -13,13 +13,19 @@ #include <objtool/warn.h> #include <objtool/endianness.h> -static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi) +static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, + struct instruction *insn) { - struct instruction *insn = container_of(cfi, struct instruction, cfi); struct cfi_reg *bp = &cfi->regs[CFI_BP]; memset(orc, 0, sizeof(*orc)); + if (!cfi) { + orc->end = 0; + orc->sp_reg = ORC_REG_UNDEFINED; + return 0; + } + orc->end = cfi->end; if (cfi->cfa.base == CFI_UNDEFINED) { @@ -162,7 +168,7 @@ int orc_create(struct objtool_file *file) int i; if (!alt_group) { - if (init_orc_entry(&orc, &insn->cfi)) + if (init_orc_entry(&orc, insn->cfi, insn)) return -1; if (!memcmp(&prev_orc, &orc, sizeof(orc))) continue; @@ -186,7 +192,8 @@ int orc_create(struct objtool_file *file) struct cfi_state *cfi = alt_group->cfi[i]; if (!cfi) continue; - if (init_orc_entry(&orc, cfi)) + /* errors are reported on the original insn */ + if (init_orc_entry(&orc, cfi, insn)) return -1; if (!memcmp(&prev_orc, &orc, sizeof(orc))) continue; @@ -204,7 +211,7 @@ int orc_create(struct objtool_file *file) /* Add a section terminator */ if (!empty) { - orc_list_add(&orc_list, &null, sec, sec->len); + orc_list_add(&orc_list, &null, sec, sec->sh.sh_size); nr++; } } diff --git a/tools/objtool/special.c b/tools/objtool/special.c index f1428e32a505..e2223dd91c37 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -58,22 +58,11 @@ void __weak arch_handle_alternative(unsigned short feature, struct special_alt * { } -static bool reloc2sec_off(struct reloc *reloc, struct section **sec, unsigned long *off) +static void reloc_to_sec_off(struct reloc *reloc, struct section **sec, + unsigned long *off) { - switch (reloc->sym->type) { - case STT_FUNC: - *sec = reloc->sym->sec; - *off = reloc->sym->offset + reloc->addend; - return true; - - case STT_SECTION: - *sec = reloc->sym->sec; - *off = reloc->addend; - return true; - - default: - return false; - } + *sec = reloc->sym->sec; + *off = reloc->sym->offset + reloc->addend; } static int get_alt_entry(struct elf *elf, struct special_entry *entry, @@ -109,13 +98,8 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); return -1; } - if (!reloc2sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off)) { - WARN_FUNC("don't know how to handle reloc symbol type %d: %s", - sec, offset + entry->orig, - orig_reloc->sym->type, - orig_reloc->sym->name); - return -1; - } + + reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off); if (!entry->group || alt->new_len) { new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); @@ -125,21 +109,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, return -1; } - /* - * Skip retpoline .altinstr_replacement... we already rewrite the - * instructions for retpolines anyway, see arch_is_retpoline() - * usage in add_{call,jump}_destinations(). - */ - if (arch_is_retpoline(new_reloc->sym)) - return 1; - - if (!reloc2sec_off(new_reloc, &alt->new_sec, &alt->new_off)) { - WARN_FUNC("don't know how to handle reloc symbol type %d: %s", - sec, offset + entry->new, - new_reloc->sym->type, - new_reloc->sym->name); - return -1; - } + reloc_to_sec_off(new_reloc, &alt->new_sec, &alt->new_off); /* _ASM_EXTABLE_EX hack */ if (alt->new_off >= 0x7ffffff0) @@ -181,13 +151,13 @@ int special_get_alts(struct elf *elf, struct list_head *alts) if (!sec) continue; - if (sec->len % entry->size != 0) { + if (sec->sh.sh_size % entry->size != 0) { WARN("%s size not a multiple of %d", sec->name, entry->size); return -1; } - nr_entries = sec->len / entry->size; + nr_entries = sec->sh.sh_size / entry->size; for (idx = 0; idx < nr_entries; idx++) { alt = malloc(sizeof(*alt)); diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 446180401e26..14e3e8d702a0 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -143,7 +143,7 @@ FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto ifdef CSINCLUDES LIBOPENCSD_CFLAGS := -I$(CSINCLUDES) endif -OPENCSDLIBS := -lopencsd_c_api -lopencsd +OPENCSDLIBS := -lopencsd_c_api -lopencsd -lstdc++ ifdef CSLIBS LIBOPENCSD_LDFLAGS := -L$(CSLIBS) endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index e04313c4d840..b856afa6eb52 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -787,6 +787,8 @@ $(OUTPUT)dlfilters/%.o: dlfilters/%.c include/perf/perf_dlfilter.h $(Q)$(MKDIR) -p $(OUTPUT)dlfilters $(QUIET_CC)$(CC) -c -Iinclude $(EXTRA_CFLAGS) -o $@ -fpic $< +.SECONDARY: $(DLFILTERS:.so=.o) + $(OUTPUT)dlfilters/%.so: $(OUTPUT)dlfilters/%.o $(QUIET_LINK)$(CC) $(EXTRA_CFLAGS) -shared -o $@ $< @@ -802,7 +804,7 @@ endif $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h) -LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(LDFLAGS)' +LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(filter-out -static,$(LDFLAGS))' $(LIBTRACEEVENT): FORCE $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 3018a054526a..20cd6244863b 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -45,7 +45,7 @@ static const Dwfl_Callbacks offline_callbacks = { */ static int check_return_reg(int ra_regno, Dwarf_Frame *frame) { - Dwarf_Op ops_mem[2]; + Dwarf_Op ops_mem[3]; Dwarf_Op dummy; Dwarf_Op *ops = &dummy; size_t nops; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 6211d0b84b7a..c32c2eb16d7d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -459,7 +459,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(WEIGHT) && - evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT", PERF_OUTPUT_WEIGHT)) + evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT)) return -EINVAL; if (PRINT_FIELD(SYM) && @@ -4039,11 +4039,15 @@ script_found: goto out_delete; uname(&uts); - if (data.is_pipe || /* assume pipe_mode indicates native_arch */ - !strcmp(uts.machine, session->header.env.arch) || - (!strcmp(uts.machine, "x86_64") && - !strcmp(session->header.env.arch, "i386"))) + if (data.is_pipe) { /* Assume pipe_mode indicates native_arch */ native_arch = true; + } else if (session->header.env.arch) { + if (!strcmp(uts.machine, session->header.env.arch)) + native_arch = true; + else if (!strcmp(uts.machine, "x86_64") && + !strcmp(session->header.env.arch, "i386")) + native_arch = true; + } script.session = session; script__setup_sample_type(&script); diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 6731b3cf0c2f..7c887d37b893 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -1285,6 +1285,7 @@ int main(int argc, char *argv[]) } free_arch_std_events(); + free_sys_event_tables(); free(mapfile); return 0; @@ -1306,6 +1307,7 @@ err_close_eventsfp: create_empty_mapping(output_file); err_out: free_arch_std_events(); + free_sys_event_tables(); free(mapfile); return ret; } diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index d9e99b3f77e6..d8ea6a88163f 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -68,3 +68,100 @@ fd=10 type=0 config=5 optional=1 + +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index 8b04a055d154..b656ab93c5bf 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 4fca9f1bfbf8..97625090a1c4 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 @@ -114,8 +211,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event15:base-stat] -fd=15 +[event24:base-stat] +fd=24 type=3 config=1 optional=1 @@ -124,8 +221,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event16:base-stat] -fd=16 +[event25:base-stat] +fd=25 type=3 config=65537 optional=1 @@ -134,8 +231,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event17:base-stat] -fd=17 +[event26:base-stat] +fd=26 type=3 config=3 optional=1 @@ -144,8 +241,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event18:base-stat] -fd=18 +[event27:base-stat] +fd=27 type=3 config=65539 optional=1 @@ -154,8 +251,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event19:base-stat] -fd=19 +[event28:base-stat] +fd=28 type=3 config=4 optional=1 @@ -164,8 +261,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event20:base-stat] -fd=20 +[event29:base-stat] +fd=29 type=3 config=65540 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index 4bb58e1c82a6..d555042e3fbf 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 @@ -114,8 +211,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event15:base-stat] -fd=15 +[event24:base-stat] +fd=24 type=3 config=1 optional=1 @@ -124,8 +221,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event16:base-stat] -fd=16 +[event25:base-stat] +fd=25 type=3 config=65537 optional=1 @@ -134,8 +231,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event17:base-stat] -fd=17 +[event26:base-stat] +fd=26 type=3 config=3 optional=1 @@ -144,8 +241,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event18:base-stat] -fd=18 +[event27:base-stat] +fd=27 type=3 config=65539 optional=1 @@ -154,8 +251,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event19:base-stat] -fd=19 +[event28:base-stat] +fd=28 type=3 config=4 optional=1 @@ -164,8 +261,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event20:base-stat] -fd=20 +[event29:base-stat] +fd=29 type=3 config=65540 optional=1 @@ -174,8 +271,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event21:base-stat] -fd=21 +[event30:base-stat] +fd=30 type=3 config=512 optional=1 @@ -184,8 +281,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event22:base-stat] -fd=22 +[event31:base-stat] +fd=31 type=3 config=66048 optional=1 diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index f0e75df72b80..3167b4628b6d 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -301,6 +301,16 @@ static const char * const mem_lvlnum[] = { [PERF_MEM_LVLNUM_NA] = "N/A", }; +static const char * const mem_hops[] = { + "N/A", + /* + * While printing, 'Remote' will be added to represent + * 'Remote core, same node' accesses as remote field need + * to be set with mem_hops field. + */ + "core, same node", +}; + int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) { size_t i, l = 0; @@ -320,12 +330,14 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) /* already taken care of */ m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); - if (mem_info && mem_info->data_src.mem_remote) { strcat(out, "Remote "); l += 7; } + if (mem_info && mem_info->data_src.mem_hops) + l += scnprintf(out + l, sz - l, "%s ", mem_hops[mem_info->data_src.mem_hops]); + printed = 0; for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) { if (!(m & 0x1)) @@ -472,8 +484,12 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi) /* * Skylake might report unknown remote level via this * bit, consider it when evaluating remote HITMs. + * + * Incase of power, remote field can also be used to denote cache + * accesses from the another core of same node. Hence, setting + * mrem only when HOPS is zero along with set remote field. */ - bool mrem = data_src->mem_remote; + bool mrem = (data_src->mem_remote && !data_src->mem_hops); int err = 0; #define HITM_INC(__f) \ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 069c2cfdd3be..352f16076e01 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2116,7 +2116,7 @@ fetch_decomp_event(u64 head, size_t mmap_size, char *buf, bool needs_swap) static int __perf_session__process_decomp_events(struct perf_session *session) { s64 skip; - u64 size, file_pos = 0; + u64 size; struct decomp *decomp = session->decomp_last; if (!decomp) @@ -2132,7 +2132,7 @@ static int __perf_session__process_decomp_events(struct perf_session *session) size = event->header.size; if (size < sizeof(struct perf_event_header) || - (skip = perf_session__process_event(session, event, file_pos)) < 0) { + (skip = perf_session__process_event(session, event, decomp->file_pos)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", decomp->file_pos + decomp->head, event->header.size, event->header.type); return -EINVAL; diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 5a931456e718..ac35c61f65f5 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -16,7 +16,7 @@ assert sys.version_info >= (3, 7), "Python version is too old" from collections import namedtuple from enum import Enum, auto -from typing import Iterable +from typing import Iterable, Sequence import kunit_config import kunit_json @@ -186,6 +186,26 @@ def run_tests(linux: kunit_kernel.LinuxSourceTree, exec_result.elapsed_time)) return parse_result +# Problem: +# $ kunit.py run --json +# works as one would expect and prints the parsed test results as JSON. +# $ kunit.py run --json suite_name +# would *not* pass suite_name as the filter_glob and print as json. +# argparse will consider it to be another way of writing +# $ kunit.py run --json=suite_name +# i.e. it would run all tests, and dump the json to a `suite_name` file. +# So we hackily automatically rewrite --json => --json=stdout +pseudo_bool_flag_defaults = { + '--json': 'stdout', + '--raw_output': 'kunit', +} +def massage_argv(argv: Sequence[str]) -> Sequence[str]: + def massage_arg(arg: str) -> str: + if arg not in pseudo_bool_flag_defaults: + return arg + return f'{arg}={pseudo_bool_flag_defaults[arg]}' + return list(map(massage_arg, argv)) + def add_common_opts(parser) -> None: parser.add_argument('--build_dir', help='As in the make command, it specifies the build ' @@ -303,7 +323,7 @@ def main(argv, linux=None): help='Specifies the file to read results from.', type=str, nargs='?', metavar='input_file') - cli_args = parser.parse_args(argv) + cli_args = parser.parse_args(massage_argv(argv)) if get_kernel_root_path(): os.chdir(get_kernel_root_path()) diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 619c4554cbff..1edcc8373b4e 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -408,6 +408,14 @@ class KUnitMainTest(unittest.TestCase): self.assertNotEqual(call, mock.call(StrContains('Testing complete.'))) self.assertNotEqual(call, mock.call(StrContains(' 0 tests run'))) + def test_run_raw_output_does_not_take_positional_args(self): + # --raw_output is a string flag, but we don't want it to consume + # any positional arguments, only ones after an '=' + self.linux_source_mock.run_kernel = mock.Mock(return_value=[]) + kunit.main(['run', '--raw_output', 'filter_glob'], self.linux_source_mock) + self.linux_source_mock.run_kernel.assert_called_once_with( + args=None, build_dir='.kunit', filter_glob='filter_glob', timeout=300) + def test_exec_timeout(self): timeout = 3453 kunit.main(['exec', '--timeout', str(timeout)], self.linux_source_mock) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 5c5979046523..d88bb65b74cc 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -949,7 +949,6 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, int err, n; u32 key; char b; - int retries = 100; zero_verdict_count(verd_mapfd); @@ -1002,17 +1001,11 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, goto close_peer1; if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_peer1: xclose(p1); @@ -1571,7 +1564,6 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; int sfd[2]; u32 key; @@ -1606,17 +1598,11 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close: xclose(c1); @@ -1748,7 +1734,6 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; u32 key; char b; @@ -1781,17 +1766,11 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_cli1: xclose(c1); @@ -1841,7 +1820,6 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, const char *log_prefix = redir_mode_str(mode); int c0, c1, p0, p1; unsigned int pass; - int retries = 100; int err, n; int sfd[2]; u32 key; @@ -1876,17 +1854,11 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close_cli1: xclose(c1); @@ -1932,7 +1904,6 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, int sfd[2]; u32 key; char b; - int retries = 100; zero_verdict_count(verd_mapfd); @@ -1963,17 +1934,11 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); -again: - n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) { - if (errno == EAGAIN && retries--) { - usleep(1000); - goto again; - } - FAIL_ERRNO("%s: read", log_prefix); - } + n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC); + if (n < 0) + FAIL_ERRNO("%s: recv_timeout", log_prefix); if (n == 0) - FAIL("%s: incomplete read", log_prefix); + FAIL("%s: incomplete recv", log_prefix); close: xclose(c1); diff --git a/tools/testing/selftests/drivers/dma-buf/udmabuf.c b/tools/testing/selftests/drivers/dma-buf/udmabuf.c index 4de902ea14d8..de1c4e6de0b2 100644 --- a/tools/testing/selftests/drivers/dma-buf/udmabuf.c +++ b/tools/testing/selftests/drivers/dma-buf/udmabuf.c @@ -1,10 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <string.h> #include <errno.h> -#include <linux/fcntl.h> +#include <fcntl.h> #include <malloc.h> #include <sys/ioctl.h> diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc index 5f5b2ba3e557..60c02b482be8 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc @@ -11,8 +11,8 @@ SYSTEM="syscalls" EVENT="sys_enter_openat" FIELD="filename" EPROBE="eprobe_open" - -echo "e:$EPROBE $SYSTEM/$EVENT file=+0(\$filename):ustring" >> dynamic_events +OPTIONS="file=+0(\$filename):ustring" +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events grep -q "$EPROBE" dynamic_events test -d events/eprobes/$EPROBE @@ -37,4 +37,54 @@ echo "-:$EPROBE" >> dynamic_events ! grep -q "$EPROBE" dynamic_events ! test -d events/eprobes/$EPROBE +# test various ways to remove the probe (already tested with just event name) + +# With group name +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With group name and system/event +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE $SYSTEM/$EVENT" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With just event name and system/event +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:$EPROBE $SYSTEM/$EVENT" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With just event name and system/event and options +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# With group name and system/event and options +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +grep -q "$EPROBE" dynamic_events +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + +# Finally make sure what is in the dynamic_events file clears it too +echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +LINE=`sed -e '/$EPROBE/s/^e/-/' < dynamic_events` +test -d events/eprobes/$EPROBE +echo "-:eprobes/$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events +! grep -q "$EPROBE" dynamic_events +! test -d events/eprobes/$EPROBE + clear_trace diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index 0e78b49d0f2f..fbcbdb6963b3 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -8,3 +8,4 @@ futex_wait_uninitialized_heap futex_wait_wouldblock futex_wait futex_requeue +futex_waitv diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index bd1fec59e010..5cc38de9d8ea 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -17,7 +17,8 @@ TEST_GEN_FILES := \ futex_wait_uninitialized_heap \ futex_wait_private_mapped_file \ futex_wait \ - futex_requeue + futex_requeue \ + futex_waitv TEST_PROGS := run.sh diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c index 1f8f6daaf1e7..3651ce17beeb 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c +++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c @@ -17,6 +17,7 @@ #include <pthread.h> #include "futextest.h" +#include "futex2test.h" #include "logging.h" #define TEST_NAME "futex-wait-timeout" @@ -96,6 +97,12 @@ int main(int argc, char *argv[]) struct timespec to; pthread_t thread; int c; + struct futex_waitv waitv = { + .uaddr = (uintptr_t)&f1, + .val = f1, + .flags = FUTEX_32, + .__reserved = 0 + }; while ((c = getopt(argc, argv, "cht:v:")) != -1) { switch (c) { @@ -118,7 +125,7 @@ int main(int argc, char *argv[]) } ksft_print_header(); - ksft_set_plan(7); + ksft_set_plan(9); ksft_print_msg("%s: Block on a futex and wait for timeout\n", basename(argv[0])); ksft_print_msg("\tArguments: timeout=%ldns\n", timeout_ns); @@ -175,6 +182,18 @@ int main(int argc, char *argv[]) res = futex_lock_pi(&futex_pi, NULL, 0, FUTEX_CLOCK_REALTIME); test_timeout(res, &ret, "futex_lock_pi invalid timeout flag", ENOSYS); + /* futex_waitv with CLOCK_MONOTONIC */ + if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns)) + return RET_FAIL; + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC); + test_timeout(res, &ret, "futex_waitv monotonic", ETIMEDOUT); + + /* futex_waitv with CLOCK_REALTIME */ + if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns)) + return RET_FAIL; + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_REALTIME); + test_timeout(res, &ret, "futex_waitv realtime", ETIMEDOUT); + ksft_print_cnts(); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c index 0ae390ff8164..7d7a6a06cdb7 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c +++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c @@ -22,6 +22,7 @@ #include <string.h> #include <time.h> #include "futextest.h" +#include "futex2test.h" #include "logging.h" #define TEST_NAME "futex-wait-wouldblock" @@ -42,6 +43,12 @@ int main(int argc, char *argv[]) futex_t f1 = FUTEX_INITIALIZER; int res, ret = RET_PASS; int c; + struct futex_waitv waitv = { + .uaddr = (uintptr_t)&f1, + .val = f1+1, + .flags = FUTEX_32, + .__reserved = 0 + }; while ((c = getopt(argc, argv, "cht:v:")) != -1) { switch (c) { @@ -61,18 +68,44 @@ int main(int argc, char *argv[]) } ksft_print_header(); - ksft_set_plan(1); + ksft_set_plan(2); ksft_print_msg("%s: Test the unexpected futex value in FUTEX_WAIT\n", basename(argv[0])); info("Calling futex_wait on f1: %u @ %p with val=%u\n", f1, &f1, f1+1); res = futex_wait(&f1, f1+1, &to, FUTEX_PRIVATE_FLAG); if (!res || errno != EWOULDBLOCK) { - fail("futex_wait returned: %d %s\n", - res ? errno : res, res ? strerror(errno) : ""); + ksft_test_result_fail("futex_wait returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_wait\n"); } - print_result(TEST_NAME, ret); + if (clock_gettime(CLOCK_MONOTONIC, &to)) { + error("clock_gettime failed\n", errno); + return errno; + } + + to.tv_nsec += timeout_ns; + + if (to.tv_nsec >= 1000000000) { + to.tv_sec++; + to.tv_nsec -= 1000000000; + } + + info("Calling futex_waitv on f1: %u @ %p with val=%u\n", f1, &f1, f1+1); + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC); + if (!res || errno != EWOULDBLOCK) { + ksft_test_result_pass("futex_waitv returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv\n"); + } + + ksft_print_cnts(); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_waitv.c b/tools/testing/selftests/futex/functional/futex_waitv.c new file mode 100644 index 000000000000..a94337f677e1 --- /dev/null +++ b/tools/testing/selftests/futex/functional/futex_waitv.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * futex_waitv() test by André Almeida <andrealmeid@collabora.com> + * + * Copyright 2021 Collabora Ltd. + */ + +#include <errno.h> +#include <error.h> +#include <getopt.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <pthread.h> +#include <stdint.h> +#include <sys/shm.h> +#include "futextest.h" +#include "futex2test.h" +#include "logging.h" + +#define TEST_NAME "futex-wait" +#define WAKE_WAIT_US 10000 +#define NR_FUTEXES 30 +static struct futex_waitv waitv[NR_FUTEXES]; +u_int32_t futexes[NR_FUTEXES] = {0}; + +void usage(char *prog) +{ + printf("Usage: %s\n", prog); + printf(" -c Use color\n"); + printf(" -h Display this help message\n"); + printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n", + VQUIET, VCRITICAL, VINFO); +} + +void *waiterfn(void *arg) +{ + struct timespec to; + int res; + + /* setting absolute timeout for futex2 */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res < 0) { + ksft_test_result_fail("futex_waitv returned: %d %s\n", + errno, strerror(errno)); + } else if (res != NR_FUTEXES - 1) { + ksft_test_result_fail("futex_waitv returned: %d, expecting %d\n", + res, NR_FUTEXES - 1); + } + + return NULL; +} + +int main(int argc, char *argv[]) +{ + pthread_t waiter; + int res, ret = RET_PASS; + struct timespec to; + int c, i; + + while ((c = getopt(argc, argv, "cht:v:")) != -1) { + switch (c) { + case 'c': + log_color(1); + break; + case 'h': + usage(basename(argv[0])); + exit(0); + case 'v': + log_verbosity(atoi(optarg)); + break; + default: + usage(basename(argv[0])); + exit(1); + } + } + + ksft_print_header(); + ksft_set_plan(7); + ksft_print_msg("%s: Test FUTEX_WAITV\n", + basename(argv[0])); + + for (i = 0; i < NR_FUTEXES; i++) { + waitv[i].uaddr = (uintptr_t)&futexes[i]; + waitv[i].flags = FUTEX_32 | FUTEX_PRIVATE_FLAG; + waitv[i].val = 0; + waitv[i].__reserved = 0; + } + + /* Private waitv */ + if (pthread_create(&waiter, NULL, waiterfn, NULL)) + error("pthread_create failed\n", errno); + + usleep(WAKE_WAIT_US); + + res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, FUTEX_PRIVATE_FLAG); + if (res != 1) { + ksft_test_result_fail("futex_wake private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv private\n"); + } + + /* Shared waitv */ + for (i = 0; i < NR_FUTEXES; i++) { + int shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666); + + if (shm_id < 0) { + perror("shmget"); + exit(1); + } + + unsigned int *shared_data = shmat(shm_id, NULL, 0); + + *shared_data = 0; + waitv[i].uaddr = (uintptr_t)shared_data; + waitv[i].flags = FUTEX_32; + waitv[i].val = 0; + waitv[i].__reserved = 0; + } + + if (pthread_create(&waiter, NULL, waiterfn, NULL)) + error("pthread_create failed\n", errno); + + usleep(WAKE_WAIT_US); + + res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, 0); + if (res != 1) { + ksft_test_result_fail("futex_wake shared returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv shared\n"); + } + + for (i = 0; i < NR_FUTEXES; i++) + shmdt(u64_to_ptr(waitv[i].uaddr)); + + /* Testing a waiter without FUTEX_32 flag */ + waitv[0].flags = FUTEX_PRIVATE_FLAG; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv without FUTEX_32\n"); + } + + /* Testing a waiter with an unaligned address */ + waitv[0].flags = FUTEX_PRIVATE_FLAG | FUTEX_32; + waitv[0].uaddr = 1; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_wake private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv with an unaligned address\n"); + } + + /* Testing a NULL address for waiters.uaddr */ + waitv[0].uaddr = 0x00000000; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv NULL address in waitv.uaddr\n"); + } + + /* Testing a NULL address for *waiters */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(NULL, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv NULL address in *waiters\n"); + } + + /* Testing an invalid clockid */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(NULL, NR_FUTEXES, 0, &to, CLOCK_TAI); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv invalid clockid\n"); + } + + ksft_print_cnts(); + return ret; +} diff --git a/tools/testing/selftests/futex/functional/run.sh b/tools/testing/selftests/futex/functional/run.sh index 11a9d62290f5..5ccd599da6c3 100755 --- a/tools/testing/selftests/futex/functional/run.sh +++ b/tools/testing/selftests/futex/functional/run.sh @@ -79,3 +79,6 @@ echo echo ./futex_requeue $COLOR + +echo +./futex_waitv $COLOR diff --git a/tools/testing/selftests/futex/include/futex2test.h b/tools/testing/selftests/futex/include/futex2test.h new file mode 100644 index 000000000000..9d305520e849 --- /dev/null +++ b/tools/testing/selftests/futex/include/futex2test.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Futex2 library addons for futex tests + * + * Copyright 2021 Collabora Ltd. + */ +#include <stdint.h> + +#define u64_to_ptr(x) ((void *)(uintptr_t)(x)) + +/** + * futex_waitv - Wait at multiple futexes, wake on any + * @waiters: Array of waiters + * @nr_waiters: Length of waiters array + * @flags: Operation flags + * @timo: Optional timeout for operation + */ +static inline int futex_waitv(volatile struct futex_waitv *waiters, unsigned long nr_waiters, + unsigned long flags, struct timespec *timo, clockid_t clockid) +{ + return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, timo, clockid); +} diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 21b646d10b88..86ab429fe7f3 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -43,3 +43,4 @@ CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_ACT_MIRRED=m CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y +CONFIG_CRYPTO_SM4=y diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 13350cd5c8ac..3313566ce906 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -289,6 +289,12 @@ set_sysctl() run_cmd sysctl -q -w $* } +# get sysctl values in NS-A +get_sysctl() +{ + ${NSA_CMD} sysctl -n $* +} + ################################################################################ # Setup for tests @@ -439,10 +445,13 @@ cleanup() ip -netns ${NSA} link set dev ${NSA_DEV} down ip -netns ${NSA} link del dev ${NSA_DEV} + ip netns pids ${NSA} | xargs kill 2>/dev/null ip netns del ${NSA} fi + ip netns pids ${NSB} | xargs kill 2>/dev/null ip netns del ${NSB} + ip netns pids ${NSC} | xargs kill 2>/dev/null ip netns del ${NSC} >/dev/null 2>&1 } @@ -1003,6 +1012,60 @@ ipv4_tcp_md5() run_cmd nettest -s -I ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET} log_test $? 1 "MD5: VRF: Device must be a VRF - prefix" + test_ipv4_md5_vrf__vrf_server__no_bind_ifindex + test_ipv4_md5_vrf__global_server__bind_ifindex0 +} + +test_ipv4_md5_vrf__vrf_server__no_bind_ifindex() +{ + log_start + show_hint "Simulates applications using VRF without TCP_MD5SIG_FLAG_IFINDEX" + run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: VRF-bound server, unbound key accepts connection" + + log_start + show_hint "Binding both the socket and the key is not required but it works" + run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: VRF-bound server, bound key accepts connection" +} + +test_ipv4_md5_vrf__global_server__bind_ifindex0() +{ + # This particular test needs tcp_l3mdev_accept=1 for Global server to accept VRF connections + local old_tcp_l3mdev_accept + old_tcp_l3mdev_accept=$(get_sysctl net.ipv4.tcp_l3mdev_accept) + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 2 "MD5: VRF: Global server, Key bound to ifindex=0 rejects VRF connection" + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key bound to ifindex=0 accepts non-VRF connection" + log_start + + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts VRF connection" + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts non-VRF connection" + + # restore value + set_sysctl net.ipv4.tcp_l3mdev_accept="$old_tcp_l3mdev_accept" } ipv4_tcp_novrf() diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index d97bd6889446..72ee644d47bf 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -9,6 +9,7 @@ TEST_PROGS = bridge_igmp.sh \ gre_inner_v4_multipath.sh \ gre_inner_v6_multipath.sh \ gre_multipath.sh \ + ip6_forward_instats_vrf.sh \ ip6gre_inner_v4_multipath.sh \ ip6gre_inner_v6_multipath.sh \ ipip_flat_gre_key.sh \ diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index b802c14d2950..e5e2fbeca22e 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -39,3 +39,5 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# IPv6 traceroute utility name. +TROUTE6=traceroute6 diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh new file mode 100755 index 000000000000..9f5b3e2e5e95 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh @@ -0,0 +1,172 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test ipv6 stats on the incoming if when forwarding with VRF + +ALL_TESTS=" + ipv6_ping + ipv6_in_too_big_err + ipv6_in_hdr_err + ipv6_in_addr_err + ipv6_in_discard +" + +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 2001:1:1::2/64 + ip -6 route add vrf v$h1 2001:1:2::/64 via 2001:1:1::1 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 2001:1:2::/64 via 2001:1:1::1 + simple_if_fini $h1 2001:1:1::2/64 +} + +router_create() +{ + vrf_create router + __simple_if_init $rtr1 router 2001:1:1::1/64 + __simple_if_init $rtr2 router 2001:1:2::1/64 + mtu_set $rtr2 1280 +} + +router_destroy() +{ + mtu_restore $rtr2 + __simple_if_fini $rtr2 2001:1:2::1/64 + __simple_if_fini $rtr1 2001:1:1::1/64 + vrf_destroy router +} + +h2_create() +{ + simple_if_init $h2 2001:1:2::2/64 + ip -6 route add vrf v$h2 2001:1:1::/64 via 2001:1:2::1 + mtu_set $h2 1280 +} + +h2_destroy() +{ + mtu_restore $h2 + ip -6 route del vrf v$h2 2001:1:1::/64 via 2001:1:2::1 + simple_if_fini $h2 2001:1:2::2/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rtr1=${NETIFS[p2]} + + rtr2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + h1_create + router_create + h2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + h2_destroy + router_destroy + h1_destroy + vrf_cleanup +} + +ipv6_in_too_big_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors) + local vrf_name=$(master_name_get $h1) + + # Send too big packets + ip vrf exec $vrf_name \ + $PING6 -s 1300 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + + local t1=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InTooBigErrors" +} + +ipv6_in_hdr_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InHdrErrors) + local vrf_name=$(master_name_get $h1) + + # Send packets with hop limit 1, easiest with traceroute6 as some ping6 + # doesn't allow hop limit to be specified + ip vrf exec $vrf_name \ + $TROUTE6 2001:1:2::2 &> /dev/null + + local t1=$(ipv6_stats_get $rtr1 Ip6InHdrErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InHdrErrors" +} + +ipv6_in_addr_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InAddrErrors) + local vrf_name=$(master_name_get $h1) + + # Disable forwarding temporary while sending the packet + sysctl -qw net.ipv6.conf.all.forwarding=0 + ip vrf exec $vrf_name \ + $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + sysctl -qw net.ipv6.conf.all.forwarding=1 + + local t1=$(ipv6_stats_get $rtr1 Ip6InAddrErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InAddrErrors" +} + +ipv6_in_discard() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InDiscards) + local vrf_name=$(master_name_get $h1) + + # Add a policy to discard + ip xfrm policy add dst 2001:1:2::2/128 dir fwd action block + ip vrf exec $vrf_name \ + $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + ip xfrm policy del dst 2001:1:2::2/128 dir fwd + + local t1=$(ipv6_stats_get $rtr1 Ip6InDiscards) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InDiscards" +} +ipv6_ping() +{ + RET=0 + + ping6_test $h1 2001:1:2::2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index e7fc5c35b569..92087d423bcf 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -751,6 +751,14 @@ qdisc_parent_stats_get() | jq '.[] | select(.parent == "'"$parent"'") | '"$selector" } +ipv6_stats_get() +{ + local dev=$1; shift + local stat=$1; shift + + cat /proc/net/dev_snmp6/$dev | grep "^$stat" | cut -f2 +} + humanize() { local speed=$1; shift diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index 3caf72bb9c6a..a2489ec398fe 100755 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -468,10 +468,26 @@ out_bits() for i in {0..22} do ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ - prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0 - - run_test "out_bit$i" "${desc/<n>/$i}" ioam-node-alpha ioam-node-beta \ - db01::2 db01::1 veth0 ${bit2type[$i]} 123 + prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ + dev veth0 &>/dev/null + + local cmd_res=$? + local descr="${desc/<n>/$i}" + + if [[ $i -ge 12 && $i -le 21 ]] + then + if [ $cmd_res != 0 ] + then + npassed=$((npassed+1)) + log_test_passed "$descr" + else + nfailed=$((nfailed+1)) + log_test_failed "$descr" + fi + else + run_test "out_bit$i" "$descr" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 ${bit2type[$i]} 123 + fi done bit2size[22]=$tmp @@ -544,7 +560,7 @@ in_bits() local tmp=${bit2size[22]} bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) )) - for i in {0..22} + for i in {0..11} {22..22} do ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0 diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c index d376cb2c383c..8f6997d35816 100644 --- a/tools/testing/selftests/net/ioam6_parser.c +++ b/tools/testing/selftests/net/ioam6_parser.c @@ -94,16 +94,6 @@ enum { TEST_OUT_BIT9, TEST_OUT_BIT10, TEST_OUT_BIT11, - TEST_OUT_BIT12, - TEST_OUT_BIT13, - TEST_OUT_BIT14, - TEST_OUT_BIT15, - TEST_OUT_BIT16, - TEST_OUT_BIT17, - TEST_OUT_BIT18, - TEST_OUT_BIT19, - TEST_OUT_BIT20, - TEST_OUT_BIT21, TEST_OUT_BIT22, TEST_OUT_FULL_SUPP_TRACE, @@ -125,16 +115,6 @@ enum { TEST_IN_BIT9, TEST_IN_BIT10, TEST_IN_BIT11, - TEST_IN_BIT12, - TEST_IN_BIT13, - TEST_IN_BIT14, - TEST_IN_BIT15, - TEST_IN_BIT16, - TEST_IN_BIT17, - TEST_IN_BIT18, - TEST_IN_BIT19, - TEST_IN_BIT20, - TEST_IN_BIT21, TEST_IN_BIT22, TEST_IN_FULL_SUPP_TRACE, @@ -199,30 +179,6 @@ static int check_ioam_header(int tid, struct ioam6_trace_hdr *ioam6h, ioam6h->nodelen != 2 || ioam6h->remlen; - case TEST_OUT_BIT12: - case TEST_IN_BIT12: - case TEST_OUT_BIT13: - case TEST_IN_BIT13: - case TEST_OUT_BIT14: - case TEST_IN_BIT14: - case TEST_OUT_BIT15: - case TEST_IN_BIT15: - case TEST_OUT_BIT16: - case TEST_IN_BIT16: - case TEST_OUT_BIT17: - case TEST_IN_BIT17: - case TEST_OUT_BIT18: - case TEST_IN_BIT18: - case TEST_OUT_BIT19: - case TEST_IN_BIT19: - case TEST_OUT_BIT20: - case TEST_IN_BIT20: - case TEST_OUT_BIT21: - case TEST_IN_BIT21: - return ioam6h->overflow || - ioam6h->nodelen || - ioam6h->remlen != 1; - case TEST_OUT_BIT22: case TEST_IN_BIT22: return ioam6h->overflow || @@ -326,6 +282,66 @@ static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h, *p += sizeof(__u32); } + if (ioam6h->type.bit12) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit13) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit14) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit15) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit16) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit17) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit18) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit19) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit20) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit21) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + if (ioam6h->type.bit22) { len = cnf.sc_data ? strlen(cnf.sc_data) : 0; aligned = cnf.sc_data ? __ALIGN_KERNEL(len, 4) : 0; @@ -455,26 +471,6 @@ static int str2id(const char *tname) return TEST_OUT_BIT10; if (!strcmp("out_bit11", tname)) return TEST_OUT_BIT11; - if (!strcmp("out_bit12", tname)) - return TEST_OUT_BIT12; - if (!strcmp("out_bit13", tname)) - return TEST_OUT_BIT13; - if (!strcmp("out_bit14", tname)) - return TEST_OUT_BIT14; - if (!strcmp("out_bit15", tname)) - return TEST_OUT_BIT15; - if (!strcmp("out_bit16", tname)) - return TEST_OUT_BIT16; - if (!strcmp("out_bit17", tname)) - return TEST_OUT_BIT17; - if (!strcmp("out_bit18", tname)) - return TEST_OUT_BIT18; - if (!strcmp("out_bit19", tname)) - return TEST_OUT_BIT19; - if (!strcmp("out_bit20", tname)) - return TEST_OUT_BIT20; - if (!strcmp("out_bit21", tname)) - return TEST_OUT_BIT21; if (!strcmp("out_bit22", tname)) return TEST_OUT_BIT22; if (!strcmp("out_full_supp_trace", tname)) @@ -509,26 +505,6 @@ static int str2id(const char *tname) return TEST_IN_BIT10; if (!strcmp("in_bit11", tname)) return TEST_IN_BIT11; - if (!strcmp("in_bit12", tname)) - return TEST_IN_BIT12; - if (!strcmp("in_bit13", tname)) - return TEST_IN_BIT13; - if (!strcmp("in_bit14", tname)) - return TEST_IN_BIT14; - if (!strcmp("in_bit15", tname)) - return TEST_IN_BIT15; - if (!strcmp("in_bit16", tname)) - return TEST_IN_BIT16; - if (!strcmp("in_bit17", tname)) - return TEST_IN_BIT17; - if (!strcmp("in_bit18", tname)) - return TEST_IN_BIT18; - if (!strcmp("in_bit19", tname)) - return TEST_IN_BIT19; - if (!strcmp("in_bit20", tname)) - return TEST_IN_BIT20; - if (!strcmp("in_bit21", tname)) - return TEST_IN_BIT21; if (!strcmp("in_bit22", tname)) return TEST_IN_BIT22; if (!strcmp("in_full_supp_trace", tname)) @@ -606,16 +582,6 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { [TEST_OUT_BIT9] = check_ioam_header_and_data, [TEST_OUT_BIT10] = check_ioam_header_and_data, [TEST_OUT_BIT11] = check_ioam_header_and_data, - [TEST_OUT_BIT12] = check_ioam_header, - [TEST_OUT_BIT13] = check_ioam_header, - [TEST_OUT_BIT14] = check_ioam_header, - [TEST_OUT_BIT15] = check_ioam_header, - [TEST_OUT_BIT16] = check_ioam_header, - [TEST_OUT_BIT17] = check_ioam_header, - [TEST_OUT_BIT18] = check_ioam_header, - [TEST_OUT_BIT19] = check_ioam_header, - [TEST_OUT_BIT20] = check_ioam_header, - [TEST_OUT_BIT21] = check_ioam_header, [TEST_OUT_BIT22] = check_ioam_header_and_data, [TEST_OUT_FULL_SUPP_TRACE] = check_ioam_header_and_data, [TEST_IN_UNDEF_NS] = check_ioam_header, @@ -633,16 +599,6 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { [TEST_IN_BIT9] = check_ioam_header_and_data, [TEST_IN_BIT10] = check_ioam_header_and_data, [TEST_IN_BIT11] = check_ioam_header_and_data, - [TEST_IN_BIT12] = check_ioam_header, - [TEST_IN_BIT13] = check_ioam_header, - [TEST_IN_BIT14] = check_ioam_header, - [TEST_IN_BIT15] = check_ioam_header, - [TEST_IN_BIT16] = check_ioam_header, - [TEST_IN_BIT17] = check_ioam_header, - [TEST_IN_BIT18] = check_ioam_header, - [TEST_IN_BIT19] = check_ioam_header, - [TEST_IN_BIT20] = check_ioam_header, - [TEST_IN_BIT21] = check_ioam_header, [TEST_IN_BIT22] = check_ioam_header_and_data, [TEST_IN_FULL_SUPP_TRACE] = check_ioam_header_and_data, [TEST_FWD_FULL_SUPP_TRACE] = check_ioam_header_and_data, diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index bd6288302094..b599003eb5ba 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -28,6 +28,7 @@ #include <unistd.h> #include <time.h> #include <errno.h> +#include <getopt.h> #include <linux/xfrm.h> #include <linux/ipsec.h> @@ -101,6 +102,8 @@ struct sock_args { struct sockaddr_in6 v6; } md5_prefix; unsigned int prefix_len; + /* 0: default, -1: force off, +1: force on */ + int bind_key_ifindex; /* expected addresses and device index for connection */ const char *expected_dev; @@ -271,11 +274,14 @@ static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args } memcpy(&md5sig.tcpm_addr, addr, alen); - if (args->ifindex) { + if ((args->ifindex && args->bind_key_ifindex >= 0) || args->bind_key_ifindex >= 1) { opt = TCP_MD5SIG_EXT; md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_IFINDEX; md5sig.tcpm_ifindex = args->ifindex; + log_msg("TCP_MD5SIG_FLAG_IFINDEX set tcpm_ifindex=%d\n", md5sig.tcpm_ifindex); + } else { + log_msg("TCP_MD5SIG_FLAG_IFINDEX off\n", md5sig.tcpm_ifindex); } rc = setsockopt(sd, IPPROTO_TCP, opt, &md5sig, sizeof(md5sig)); @@ -1822,6 +1828,14 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) } #define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq" +#define OPT_FORCE_BIND_KEY_IFINDEX 1001 +#define OPT_NO_BIND_KEY_IFINDEX 1002 + +static struct option long_opts[] = { + {"force-bind-key-ifindex", 0, 0, OPT_FORCE_BIND_KEY_IFINDEX}, + {"no-bind-key-ifindex", 0, 0, OPT_NO_BIND_KEY_IFINDEX}, + {0, 0, 0, 0} +}; static void print_usage(char *prog) { @@ -1858,6 +1872,10 @@ static void print_usage(char *prog) " -M password use MD5 sum protection\n" " -X password MD5 password for client mode\n" " -m prefix/len prefix and length to use for MD5 key\n" + " --no-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX off\n" + " --force-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX on\n" + " (default: only if -I is passed)\n" + "\n" " -g grp multicast group (e.g., 239.1.1.1)\n" " -i interactive mode (default is echo and terminate)\n" "\n" @@ -1893,7 +1911,7 @@ int main(int argc, char *argv[]) * process input args */ - while ((rc = getopt(argc, argv, GETOPT_STR)) != -1) { + while ((rc = getopt_long(argc, argv, GETOPT_STR, long_opts, NULL)) != -1) { switch (rc) { case 'B': both_mode = 1; @@ -1966,6 +1984,12 @@ int main(int argc, char *argv[]) case 'M': args.password = optarg; break; + case OPT_FORCE_BIND_KEY_IFINDEX: + args.bind_key_ifindex = 1; + break; + case OPT_NO_BIND_KEY_IFINDEX: + args.bind_key_ifindex = -1; + break; case 'X': args.client_pw = optarg; break; diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 427d94816f2d..d4ffebb989f8 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -199,7 +199,6 @@ fi # test basic connectivity if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then echo "ERROR: ns1 cannot reach ns2" 1>&2 - bash exit 1 fi diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index d7e07f4c3d7f..da1c1e4b6c86 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -741,6 +741,149 @@ EOF return $lret } +# test port shadowing. +# create two listening services, one on router (ns0), one +# on client (ns2), which is masqueraded from ns1 point of view. +# ns2 sends udp packet coming from service port to ns1, on a highport. +# Later, if n1 uses same highport to connect to ns0:service, packet +# might be port-forwarded to ns2 instead. + +# second argument tells if we expect the 'fake-entry' to take effect +# (CLIENT) or not (ROUTER). +test_port_shadow() +{ + local test=$1 + local expect=$2 + local daddrc="10.0.1.99" + local daddrs="10.0.1.1" + local result="" + local logmsg="" + + echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & + nc_r=$! + + echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & + nc_c=$! + + # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. + echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + + # ns1 tries to connect to ns0:1405. With default settings this should connect + # to client, it matches the conntrack entry created above. + + result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405) + + if [ "$result" = "$expect" ] ;then + echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}" + else + echo "ERROR: portshadow test $test: got reply from \"$result\", not $expect as intended" + ret=1 + fi + + kill $nc_r $nc_c 2>/dev/null + + # flush udp entries for next test round, if any + ip netns exec "$ns0" conntrack -F >/dev/null 2>&1 +} + +# This prevents port shadow of router service via packet filter, +# packets claiming to originate from service port from internal +# network are dropped. +test_port_shadow_filter() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family filter { + chain forward { + type filter hook forward priority 0; policy accept; + meta iif veth1 udp sport 1405 drop + } +} +EOF + test_port_shadow "port-filter" "ROUTER" + + ip netns exec "$ns0" nft delete table $family filter +} + +# This prevents port shadow of router service via notrack. +test_port_shadow_notrack() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family raw { + chain prerouting { + type filter hook prerouting priority -300; policy accept; + meta iif veth0 udp dport 1405 notrack + udp dport 1405 notrack + } + chain output { + type filter hook output priority -300; policy accept; + udp sport 1405 notrack + } +} +EOF + test_port_shadow "port-notrack" "ROUTER" + + ip netns exec "$ns0" nft delete table $family raw +} + +# This prevents port shadow of router service via sport remap. +test_port_shadow_pat() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family pat { + chain postrouting { + type nat hook postrouting priority -1; policy accept; + meta iif veth1 udp sport <= 1405 masquerade to : 1406-65535 random + } +} +EOF + test_port_shadow "pat" "ROUTER" + + ip netns exec "$ns0" nft delete table $family pat +} + +test_port_shadowing() +{ + local family="ip" + + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + meta oif veth0 masquerade + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add add $family masquerade hook" + return $ksft_skip + fi + + # test default behaviour. Packet from ns1 to ns0 is redirected to ns2. + test_port_shadow "default" "CLIENT" + + # test packet filter based mitigation: prevent forwarding of + # packets claiming to come from the service port. + test_port_shadow_filter "$family" + + # test conntrack based mitigation: connections going or coming + # from router:service bypass connection tracking. + test_port_shadow_notrack "$family" + + # test nat based mitigation: fowarded packets coming from service port + # are masqueraded with random highport. + test_port_shadow_pat "$family" + + ip netns exec "$ns0" nft delete table $family nat +} # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 for i in 0 1 2; do @@ -861,6 +1004,8 @@ reset_counters $test_inet_nat && test_redirect inet $test_inet_nat && test_redirect6 inet +test_port_shadowing + if [ $ret -ne 0 ];then echo -n "FAIL: " nft --version diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c index 1af16d2c2a0a..52497b7b9f1d 100644 --- a/tools/testing/selftests/vm/split_huge_page_test.c +++ b/tools/testing/selftests/vm/split_huge_page_test.c @@ -341,7 +341,7 @@ void split_file_backed_thp(void) } /* write something to the file, so a file-backed THP can be allocated */ - num_written = write(fd, tmpfs_loc, sizeof(tmpfs_loc)); + num_written = write(fd, tmpfs_loc, strlen(tmpfs_loc) + 1); close(fd); if (num_written < 1) { diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 10ab56c2484a..60aa1a4fc69b 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -414,9 +414,6 @@ static void uffd_test_ctx_init_ext(uint64_t *features) uffd_test_ops->allocate_area((void **)&area_src); uffd_test_ops->allocate_area((void **)&area_dst); - uffd_test_ops->release_pages(area_src); - uffd_test_ops->release_pages(area_dst); - userfaultfd_open(features); count_verify = malloc(nr_pages * sizeof(unsigned long long)); @@ -437,6 +434,26 @@ static void uffd_test_ctx_init_ext(uint64_t *features) *(area_count(area_src, nr) + 1) = 1; } + /* + * After initialization of area_src, we must explicitly release pages + * for area_dst to make sure it's fully empty. Otherwise we could have + * some area_dst pages be errornously initialized with zero pages, + * hence we could hit memory corruption later in the test. + * + * One example is when THP is globally enabled, above allocate_area() + * calls could have the two areas merged into a single VMA (as they + * will have the same VMA flags so they're mergeable). When we + * initialize the area_src above, it's possible that some part of + * area_dst could have been faulted in via one huge THP that will be + * shared between area_src and area_dst. It could cause some of the + * area_dst won't be trapped by missing userfaults. + * + * This release_pages() will guarantee even if that happened, we'll + * proactively split the thp and drop any accidentally initialized + * pages within area_dst. + */ + uffd_test_ops->release_pages(area_dst); + pipefd = malloc(sizeof(int) * nr_cpus * 2); if (!pipefd) err("pipefd"); diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c index cec6f5a738e1..fa927ad16f8a 100644 --- a/tools/testing/vsock/vsock_diag_test.c +++ b/tools/testing/vsock/vsock_diag_test.c @@ -332,8 +332,6 @@ static void test_no_sockets(const struct test_opts *opts) read_vsock_stat(&sockets); check_no_sockets(&sockets); - - free_sock_stat(&sockets); } static void test_listen_socket_server(const struct test_opts *opts) |